Sluzba prijme adresu HTML dokumentu nebo HTML v tele requestu a vrati PDF. Navrzena pro dokumenty o stovkach az tisicich stranek. Rendering: - WeasyPrint jako vychozi engine, spravne CSS Paged Media, nizka pametova narocnost, bez JavaScriptu - Chromium pres Playwright pro dokumenty dokreslovane skripty - rezim auto s detekci skriptu a fallbackem pri selhani WeasyPrintu Velke dokumenty: - deleni na casti na strukturalnich hranicich, rez nikdy uvnitr tabulky nebo odstavce - dvoupruchodovy render obsahu se skutecnymi cisly stranek, pozice nadpisu se ctou z kotev hlasenych u kazde stranky - cislovani stranek bud pres CSS countery, nebo pres cislovaci vrstvu nastampovanou na hotove PDF, rozmer stranky se cte z vysledneho souboru - Chromium se restartuje po N jobech, nikdy vsak behem beziciho renderu API: - POST /convert synchronne, POST /jobs asynchronne se sledovanim stavu, stahovanim vysledku, rusenim a volitelnym callbackem - GET /health s overenim dostupnosti obou enginu a stavem fronty - OpenAPI respektuje prefix reverse proxy pres root_path Bezpecnost a provoz: - SSRF kontrola po DNS resolvu, na kazdem presmerovani a u vsech pozadavku prohlizece - nedostupne assety render nezastavi, ale hlasi se v odpovedi i v logu - fronta s omezenym poctem workeru, rozpracovane joby se pri ukonceni oznaci jako failed, nezmizi potichu - strukturovane JSON logovani s job_id - vsechny limity vypnute ve vychozim stavu Dockerfile je dvoufazovy, obsahuje zavislosti WeasyPrintu, Chromium a fonty s ceskou diakritikou. Autentizace zamerne neni implementovana, zpusob predavani neni domluveny. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
104 lines
2.5 KiB
Python
104 lines
2.5 KiB
Python
"""Application errors.
|
|
|
|
Every failure surfaces a machine readable error_code and a message in Czech,
|
|
because the message is shown to the caller.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
class ConversionError(Exception):
|
|
"""Base class for every error the conversion pipeline can raise."""
|
|
|
|
error_code = "internal_error"
|
|
status_code = 500
|
|
|
|
def __init__(self, message: str, detail: dict | None = None) -> None:
|
|
super().__init__(message)
|
|
self.message = message
|
|
self.detail = detail or {}
|
|
|
|
def to_dict(self) -> dict:
|
|
payload = {"error_code": self.error_code, "message": self.message}
|
|
if self.detail:
|
|
payload["detail"] = self.detail
|
|
return payload
|
|
|
|
|
|
class InvalidRequestError(ConversionError):
|
|
error_code = "invalid_request"
|
|
status_code = 400
|
|
|
|
|
|
class BlockedTargetError(ConversionError):
|
|
"""The requested URL points somewhere the service refuses to reach."""
|
|
|
|
error_code = "blocked_target"
|
|
status_code = 400
|
|
|
|
|
|
class SourceUnavailableError(ConversionError):
|
|
error_code = "source_unavailable"
|
|
status_code = 502
|
|
|
|
|
|
class RenderTimeoutError(ConversionError):
|
|
error_code = "render_timeout"
|
|
status_code = 504
|
|
|
|
|
|
class SyncTooLongError(ConversionError):
|
|
"""Synchronous conversion exceeded its budget, caller should use /jobs."""
|
|
|
|
error_code = "sync_too_long"
|
|
status_code = 413
|
|
|
|
|
|
class EngineUnavailableError(ConversionError):
|
|
error_code = "engine_unavailable"
|
|
status_code = 503
|
|
|
|
|
|
class UnsupportedCombinationError(ConversionError):
|
|
error_code = "unsupported_combination"
|
|
status_code = 400
|
|
|
|
|
|
class LimitExceededError(ConversionError):
|
|
error_code = "limit_exceeded"
|
|
status_code = 400
|
|
|
|
|
|
class JobNotFoundError(ConversionError):
|
|
error_code = "job_not_found"
|
|
status_code = 404
|
|
|
|
|
|
class QueueFullError(ConversionError):
|
|
error_code = "queue_full"
|
|
status_code = 503
|
|
|
|
|
|
ERROR_CLASSES = (
|
|
InvalidRequestError,
|
|
BlockedTargetError,
|
|
SourceUnavailableError,
|
|
RenderTimeoutError,
|
|
SyncTooLongError,
|
|
EngineUnavailableError,
|
|
UnsupportedCombinationError,
|
|
LimitExceededError,
|
|
JobNotFoundError,
|
|
QueueFullError,
|
|
)
|
|
|
|
STATUS_BY_CODE = {cls.error_code: cls.status_code for cls in ERROR_CLASSES}
|
|
|
|
|
|
def error_from_code(error_code: str, message: str, detail: dict | None = None) -> ConversionError:
|
|
"""Rebuild a typed error from a stored job error."""
|
|
error = ConversionError(message, detail)
|
|
error.error_code = error_code
|
|
error.status_code = STATUS_BY_CODE.get(error_code, 500)
|
|
return error
|